{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:18:37Z","timestamp":1777655917206,"version":"3.51.4"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Science and Technology Program of Guangzhou","award":["202007030007"],"award-info":[{"award-number":["202007030007"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836003"],"award-info":[{"award-number":["61836003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876121"],"award-info":[{"award-number":["61876121"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Program for Guangdong Introducing Innovative and Enterpreneurial Teams","award":["2017ZT07X183"],"award-info":[{"award-number":["2017ZT07X183"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["D2191240"],"award-info":[{"award-number":["D2191240"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022,3,1]]},"DOI":"10.1109\/tpami.2020.3023438","type":"journal-article","created":{"date-parts":[[2020,9,21]],"date-time":"2020-09-21T21:49:28Z","timestamp":1600724968000},"page":"1670-1684","source":"Crossref","is-referenced-by-count":13,"title":["Visual Grounding Via Accumulated Attention"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8587-9047","authenticated-orcid":false,"given":"Chaorui","family":"Deng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3631-256X","authenticated-orcid":false,"given":"Qi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6771-3932","authenticated-orcid":false,"given":"Qingyao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6818-2221","authenticated-orcid":false,"given":"Fuyuan","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0878-5485","authenticated-orcid":false,"given":"Fan","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8856-756X","authenticated-orcid":false,"given":"Mingkui","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.558"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.375"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref7","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"ref10","article-title":"Neural machine translation by jointly learning to align and translate","volume-title":"CoRR","volume":"abs\/1409.0473","author":"Bahdanau","year":"2014"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.475"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00808"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"CoRR","volume":"abs\/1409.1556","author":"Simonyan","year":"2014"},{"key":"ref17","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"NIPS 2014 Workshop Deep Learn."},{"key":"ref18","article-title":"Deep captioning with multimodal recurrent neural networks (m-rnn)","author":"Mao","year":"2015","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2708709"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref21","first-page":"2296","article-title":"Are you talking to a machine? Dataset and methods for multilingual image question","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gao"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.416"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref27","article-title":"Simple baseline for visual question answering","author":"Zhou","year":"2015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1181"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.93"},{"key":"ref31","first-page":"1378","article-title":"Ask me anything: Dynamic memory networks for natural language processing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kumar"},{"key":"ref32","first-page":"2397","article-title":"Dynamic memory networks for visual and textual question answering","volume-title":"Proc. 23rd Int. Conf. Mach. Learn.","author":"Xiong"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01039"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_48"},{"key":"ref41","article-title":"Action recognition using visual attention","author":"Sharma","year":"2015","journal-title":"Neural Inf. Process. Syst.: Time Ser. Workshop"},{"key":"ref42","first-page":"1462","article-title":"Draw: A recurrent neural network for image generation","author":"Gregor","year":"2015","journal-title":"Int. Conf. Mach. Learn."},{"key":"ref43","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref45","first-page":"7354","article-title":"Self-attention generative adversarial networks","author":"Zhang","year":"2019","journal-title":"Proc. Int. Conf. Mach. Learn."},{"key":"ref46","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref47","first-page":"352","article-title":"A^ 2-nets: Double attention networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref48","first-page":"1243","article-title":"Convolutional sequence to sequence learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Gehring"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1055"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n16-1174"},{"key":"ref51","first-page":"2440","article-title":"End-to-end memory networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sukhbaatar"},{"key":"ref52","article-title":"Compositional attention networks for machine reasoning","author":"Hudson","year":"2018","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref53","article-title":"A structured self-attentive sentence embedding","author":"Lin","year":"2017","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.276"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.414"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.333"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00447"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-564"},{"key":"ref66","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9703108\/09201037.pdf?arnumber=9201037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:34:17Z","timestamp":1704843257000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9201037\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,1]]},"references-count":67,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2020.3023438","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,1]]}}}